CVJan 20

VENI: Variational Encoder for Natural Illumination

arXiv:2601.14079v1h-index: 4
Originality Incremental advance
AI Analysis

This work addresses the challenge of handling spherical and rotation-equivariant illumination environments in computer vision, offering incremental improvements for inverse rendering tasks.

The paper tackled the problem of inverse rendering by proposing a rotation-equivariant variational autoencoder for modeling natural illumination on the sphere, which resulted in smoother interpolation and a more well-behaved latent space compared to previous methods.

Inverse rendering is an ill-posed problem, but priors like illumination priors, can simplify it. Existing work either disregards the spherical and rotation-equivariant nature of illumination environments or does not provide a well-behaved latent space. We propose a rotation-equivariant variational autoencoder that models natural illumination on the sphere without relying on 2D projections. To preserve the SO(2)-equivariance of environment maps, we use a novel Vector Neuron Vision Transformer (VN-ViT) as encoder and a rotation-equivariant conditional neural field as decoder. In the encoder, we reduce the equivariance from SO(3) to SO(2) using a novel SO(2)-equivariant fully connected layer, an extension of Vector Neurons. We show that our SO(2)-equivariant fully connected layer outperforms standard Vector Neurons when used in our SO(2)-equivariant model. Compared to previous methods, our variational autoencoder enables smoother interpolation in latent space and offers a more well-behaved latent space.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes